Analysis of the algorithm: From kernels to backup genes.

Kernelization section

The algorithm transformed the semantic similarity matrix to make it compatible with a kernel. Once this was done for each network and kernel type, it was integrated by kernel type. Below there is a general analysis of the properties of each matrix in the different phases of the process.

Annotations properties

Table 1. Annotation files descriptors

Net Min Max Average Standard_Deviation
biological_process 1 134 7.002706359945873 11.438149515580132
cellular_component 1 40 4.162222345933308 5.25157343549579
molecular_function 1 26 3.027285837900202 3.7141595619739753
phenotype 1 335 31.553476462477843 46.99329427183839

Matrix properties

Table 2. Similarity matrixes

Net Matrix_Dimensions Matrix_Elements Matrix_Elements_Non_Zero
cellular_component_sim 17963x17963 322669369 322651406
molecular_function_sim 17335x17335 300502225 300484890

Table 3. Filtered similarity matrixes

Table 4. Uncombined kernel matrixes

Net Kernel Matrix_Dimensions Matrix_Elements Matrix_Elements_Non_Zero
cellular_component ct 17963x17963 322669369 322669369
cellular_component el 17963x17963 322669369 322669369
cellular_component ka 17963x17963 322669369 322669369
cellular_component rf 17963x17963 322669369 322669369
molecular_function ct 17335x17335 300502225 300502225
molecular_function el 17335x17335 300502225 300502225
molecular_function ka 17335x17335 300502225 300502225
molecular_function rf 17335x17335 300502225 300502225

Table 5. Integrated kernel matrixes

Integration Kernel Matrix_Dimensions Matrix_Elements Matrix_Elements_Non_Zero
integration_mean_by_presence ct 169x169 28561 14885
integration_mean_by_presence el 169x169 28561 14885
integration_mean_by_presence ka 169x169 28561 14823
integration_mean_by_presence rf 169x169 28561 14885
mean ct 169x169 28561 14885
mean el 169x169 28561 14885
mean ka 169x169 28561 14823
mean rf 169x169 28561 14885

Weight values

Comparing types of kernel

Comparing integrations and kernel types